- – Data Architect

Data Architect – Data & Insights

Summary

We are looking for a highly experienced Data Architect (Grade 7A) to lead the design and delivery of the enterprise Data & Insights platform on Microsoft Azure. The role demands deep expertise in cloud data architecture, data models, data lake/lakehouse, vector-store based RAG systems, GenAI, Agentic AI, and governance using Microsoft Purview.

The ideal candidate has strong hands-on skills in Python, LangChain, LangGraph, Azure data services, and end-to-end SDLC execution.

Roles &

Responsibilities

Technical Skills

Mandatory

Preferred

Qualifications

Top 5 Screening Points for Recruiter

1.

Robust Azure Data Platform Architecture

Experience

Look for explicit, hands-on experience with Azure Data Lake Gen2, Synapse/Serverless SQL, Databricks/Spark, and Azure Data Factory/Synapse Pipelines.

Keywords to match: ADLS, Synapse, Databricks, Spark, ADF, Delta Lake, Lakehouse.

2.

Proven

Expertise in GenAI, RAG & Vector Stores

Candidate must have real project experience building Retrieval-Augmented Generation (RAG) systems with vector databases.

Keywords to match: RAG, vector stores, embeddings, hybrid search, Azure Cognitive Search (vector), Pinecone, Weaviate, Qdrant, LangChain, LangGraph.

3.

Solid Data

Modeling & Architecture Background

Candidate should demonstrate ability to design conceptual, logical, physical data models, and lakehouse architectures.

Keywords to match: data modeling, dimensional modeling, canonical models, Delta/Parquet, partitioning, Z-order, architecture diagrams.

4.

Microsoft

Purview & Data Governance Experience

Specific experience implementing cataloging, lineage, PII tagging, and governance frameworks.

Keywords to match:



Purview, data governance, lineage, catalog, data quality, PII/PHI classification, access policies.

5.

Strong

Python, PySpark, SQL + Hands-on Technical Delivery

Look for strong programming skills and endtoend SDLC ownership.

Keywords to match: Python, PySpark, SQL, CI/CD (Azure DevOps), Terraform/Bicep, HLD/LLD, architecture reviews, full-lifecycle delivery.

Optional Recruiter Tip (Very Useful)

Reject profiles that only list:

❌ "Azure", "GenAI", or "LangChain" without project details or outcomes.

Prioritize candidates who describe actual implementations, not tool familiarity.

- Architect and design Azure-based data lake/lakehouse platforms, domain data models, and ingestion-to-consumption pipelines.

- Develop conceptual, logical, and physical cloud data models aligned with enterprise standards.

- Architect RAG pipelines including embeddings, chunking, vector stores, hybrid retrieval, reranking, and evaluation.

- Build Agentic AI workflows using LangChain and LangGraph; design tool orchestration, memory, and safety layers.

- Implement governance with Microsoft Purview for cataloging, lineage, PII tagging, and policy enforcement.

- Ensure platform security using Entra ID, private endpoints, VNETs, Key Vault, and encryption controls.

- Lead solution architecture reviews, performance tuning,



cost optimization, and NFR engineering.

- Oversee CI/CD (Azure DevOps), IaC (Terraform/Bicep), and observability (Azure Monitor, App Insights).

- Mentor engineering teams and standardize best practices, patterns, and reusable components.

- Azure Data Platform: ADLS Gen2, Synapse/Serverless SQL, Databricks/Spark, ADF/Synapse Pipelines

- Programming: Python, PySpark, SQL

- GenAI & Agentic AI: RAG architecture, vector stores (Azure Cognitive Search, Pinecone, Weaviate, Qdrant), embeddings, reranking

- Frameworks: LangChain, LangGraph

- Data Modeling: Conceptual/logical/physical models, Delta/Parquet patterns, lakehouse modeling

- Data Governance: Microsoft Purview (catalog, lineage, classification, glossary, PII governance)

- Security: Entra ID, RBAC/ABAC, Key Vault, VNET integration, encryption

- SDLC & DevOps: Azure DevOps (CI/CD), Terraform/Bicep, ADRs, HLD/LLD documentation

- Performance & Cost Optimization across compute, storage, vector workloads, and pipelines

- Azure Fabric / OneLake; Power BI semantic modeling

- dbt for transformations and testing

- Cosmos DB, PostgreSQL, SQL Server MI

- Knowledge graphs (Neo4j) and graph-based retrieval

- LLMOps: evaluation, telemetry, safety assessment, drift monitoring

- FinOps optimization practices

- Multi-cloud experience (AWS/GCP equivalents)

- API design: REST, GraphQL, gRPC

- Bachelor's or Master's degree in Engineering, Computer Science, or related discipline.

- 12–14 years of total experience with minimum 5+ years in cloud data architecture.

- Proven experience delivering Azure-based data platforms and production-grade GenAI/RAG systems.

📌 Data Architect (Bengaluru)
🏢 TalentOla
📍 Bengaluru